Return tasks that are ready and not currently claimed.
AI agents call get_ready_tasks to retrieve information from Dag Planner without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries the state of tasks in a DAG planner—specifically those ready for execution and not yet claimed. It performs no creation, modification, deletion, or execution of tasks; it only observes and reports task state. This is a pure read operation with no side effects, matching the 'Read' category profile (search, list, get, fetch).
From the tool's definition Tool name: 'get_ready_tasks'. Description: 'Return tasks that are ready and not currently claimed.' The verb 'Return' and the passive query nature indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Return tasks that are ready and not currently claimed. It is categorised as a Read tool in the Dag Planner MCP Server, which means it retrieves data without modifying state.
Register the Dag Planner MCP server in PolicyLayer and add a rule for get_ready_tasks: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Dag Planner. Nothing to install.
get_ready_tasks is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_ready_tasks rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_ready_tasks. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_ready_tasks is provided by the Dag Planner MCP server (shubhamnegi/dag-planner-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →